This discussion paper led to a publication in the <I>Journal of Econometrics</I> (2005). Volume 125, issue 1-2, pages 77-111.

We aim to disentangle the relative contributions of (i) cognitive ability, and (ii) education on health and mortality using a structural equation model suggested by Conti et al. (2010). We extend their model by allowing for a duration dependent variable, and an ordinal educational variable. Data...

In this paper we hypothesize that education is associated with a higher efficiency of health investment, yet that this efficiency advantage is solely driven by intelligence. We operationalize efficiency of health investment as the probability of dying conditional on a certain hospital diagnosis,...

This discussion paper resulted in a publication in the <I>Journal of Applied Econometrics</I> (2000). Volume 15, issue 6, pages 547-574.<P> We analyze the impact of unemployment benefits and minimum wagesusing an equilibrium search model which allows for dispersion ofbenefits and productivity levels,...</p></i>

This discussion paper resulted in a publication in <I>Econometrica</I> (2001). Volume 69, issue 6, pages 1645-1659.<P> With panel data important issues can be resolved that can not beaddressed with cross--sectional data. A major drawback is that paneldata suffer from more severe missing data problems....</p></i>

We show that a sufficient condition for the identification ofall parameters of the censored regression model with astochastic and unobserved threshold is that the errors are jointlynormally distributed. Exclusion restrictions are not needed.

The simplest equilibrium search models depend on a few parameters that determine the joint distribution of unemployment spells, job spells, and wages. In this study we use aggregate data to estimate these key parameters for five OECD countries: (West-)Germany, The Netherlands, France, the United...

We show that a sufficient condition for the identification of all parameters of the censored regression model with a stochastic and unobserved threshold is that the errors are jointly normally distributed. Exclusion restrictions are not needed. <BR><BR>

With panel data important issues can be resolved that can not be addressed with cross--sectional data. A major drawback is that panel data suffer from more severe missing data problems. Adding a sample consisting of new units randomly drawn from the original population as replacements for units...